Plugins

Tickets entre mesas para sessões na mesma máquina. A sessão indica sua mesa com um prefixo numérico no título; o ticket nomeia uma mesa e é assumido pela primeira sessão dessa mesa que começar a trabalhar. O endereço é a mesa, então o ticket não é entregue a uma sessão que apenas esteja de passagem.

Prompt optimizer for the composer: a button in the tool row rewrites your draft through a model channel you already configured, streaming into a panel that floats above the composer without taking up layout. Your draft changes only when you click Accept — and Accept is refused while the answer is still streaming, so a half-finished reply can never be written back. It asks first when the draft carries @ references or attachments, which a whole-draft replace would flatten into plain text. No global keyboard shortcuts, and no API key ever reaches the browser: the host half makes the call.

A project-scoped memory plugin for DSH. Knowledge authoring and the plugin's own prompts are open to editing, so users can redesign the library structure and how the model is driven without changing a line of code. By default the library is built on one core idea: a project document you design yourself (a handoff by default) is the project entity; the plugin detects which project a session belongs to, binds captured knowledge to that project, and promotes what generalizes into theme and global layers. The most natural logic there is does the pre-filtering of knowledge, with controllable compression and archiving of context.

Model attribution panel for the dsh web chat — local, zero-network structural fingerprinting (template token leaks, glitch canaries, tokenizer usage-vector matching) that scores which of 29 AI vendors a session's responses most resemble, with a per-claim evidence ledger and a 12-probe active battery.

Painel de química para DSH Web. Desenha estruturas no Ketcher; um script descarrega a build, que é renderizada localmente no navegador sem backend. O RDKit calcula a molécula atual sem chamar modelos: fórmula, massas, logP, TPSA, dadores/aceitadores de H, anéis, Fsp3, centros estereogénicos, verificações Lipinski/Veber, QED, alertas PAINS/BRENK, estrutura Murcko, pesquisa SMARTS, semelhança, conversão, normalização e limpeza em lote. A aba de retrosíntese comunica com um backend substituível (Retro* por padrão) através de processo JSON entrada/saída e indica o que falta se não estiver instalado, sem inventar uma rota. Os cálculos são feitos pelo pacote Python do repositório (rdkit), instalado separadamente via pip.

Ferramentas de skill sob demanda para DeepSeek Harness: skill_search / skill_load / skill_ref pesquisam uma biblioteca em etapas e carregam o conteúdo apenas quando necessário, sem manter a biblioteca no catálogo da sessão ou no contexto de todos os turnos. A aba Skills relê a sessão e lista skills realmente carregadas e seus turnos. Sem dependências; registros são renderizados somente no cliente e nunca entram no contexto do modelo.

Security-audit facts AI coding agents cannot compute, plus a verdict gate: euthyna history attributes deleted lines to commits and flags those from security fixes (--origins finds the first introducer), euthyna coverage reports which changed symbols no test ever invoked, and euthyna gate checks each finding against six gates, downgrading any without evidence to an observation.

Adiciona Explain ao cartão de aprovação: uma chamada ao modelo retorna exatamente três linhas sobre a operação pendente, arquivos ou estado lidos/escritos/alterados/executados e veredito de risco/atenção/seguro com justificativa em uma frase. Também exibe detalhes de chamadas write/edit, que o renderizador deixa vazios por ler somente command.

Permissões de arquivos para o shell são concedidas por caminho e capacidade, não por nome do comando. A linha de comando é analisada para efeitos de leitura, escrita, criação, exclusão e execução; capacidade ausente abre um cartão de aprovação em vez de uma recusa total. As mesmas regras são compiladas no perfil macOS Seatbelt e aplicadas ao processo, aos filhos e ao código oculto nos argumentos. A aba Approvals mostra o log de auditoria e identifica a regra, revisão automática ou pessoa que respondeu a cada chamada.

Skill de atualização para autores de plugins do DeepSeek Harness: um índice detecta a faixa peer do solicitante e direciona ao closed corridor card correspondente (0.1.3-alpha.1→0.1.5-rc.1, etapas A+B; 0.1.5-rc.2→0.1.6-alpha.2, etapa C), além de scanner de limites sem dependências em skill e CLI npx.

Escopo de MCP por workspace para o DeepSeek Harness — decida quais servidores MCP uma sessão pode ver a partir do diretório em que foi aberta.

Reporta a atividade das sessões do DeepSeek Harness a um servidor cc-monitor auto-hospedado, que apresenta sessões do Claude Code e do DSH como cartões de estado com código de cores num único painel web e avisa o seu navegador e a aplicação Android quando uma sessão precisa de atenção.

Entrada de voz pronta para a China para o compositor. Requer uma ponte local em Python (pip install dashscope websockets, executar bridge/voice-bridge.py) — o plugin sozinho não funciona. O microfone do navegador transmite PCM de 16 kHz à ponte, que executa o Alibaba Cloud DashScope ASR (paraformer-realtime-v2); o texto intermediário preenche o rascunho no cursor, parada automática por silêncio, envio automático opcional.

Um interrupt button verde ao lado da caixa de envio: interrompe silenciosamente um agente em execução, que então resume seu progresso e pede seus novos requisitos, com um interrupt prompt personalizável.

Plugin do DeepSeek Harness (DSH): um seletor de "Idioma de Raciocínio" em Configurações → Geral que informa ao modelo em qual idioma raciocinar (chain of thought) por meio de uma seção do system prompt. Zero chamadas extras, zero latência, 12 idiomas.

Recursive delegation for dsh agent trees: a preset plus Host limits bound what each subagent may do, subagents work in separate _agents/ workspaces, and the parent decides which results to integrate.

Keeps a DeepSeek Harness run going on its own: continues a turn that ended abnormally, and continues a turn logged as completed while the model tool call was emitted as plain text instead, which leaves the agent silently idle. Revives a model request that stops streaming. A wait on an approval or on a question is logged and notified, never answered.

Union web search for DSH (consolidated successor of DDDMUC/dsh-free-search, which it credits): 28 engines across three tiers — keyless free (Bing/DuckDuckGo/AnySearch/SearXNG multi-instance union, plus Exa/Tavily/Keenable/Firecrawl/Parallel keyless modes), paid-with-key (Zhihu/Perplexity/Serply/DeepSeek official/You.com/Baidu/Kimi/Aliyun/Doubao/Zhipu/Bocha/Metaso), and model built-in search (OpenAI/Gemini/Claude/Grok, explicit opt-in only) — with auto smart routing, per-engine enable/disable & fallback priority, parallel top-3 merge, multi_search, failure-aware fallback, a toggle to block the system built-in search, time filtering, platform search, web_fetch and a web settings UI. Experimental free advance_fetch: whole-page GFM-Markdown or CSS-selector/fields structured extraction with no API key and no per-call billing; fetch identity configurable (custom User-Agent, Referer, per-domain cookies attached only on domain match, never leaked across cross-domain redirects). Hosts 0.1.0-rc.2 through 0.2.1-rc.2 (17-tag exact engines.dsh enum; the rc.2 search-provider takeover goes through volatile config pinning after capability probing, never version branches). Paid engines need your own API keys (optional; free engines work keyless). npm: @drscrewdriver/dsh-union-search and bare dsh-union-search.

One settings page for every MCP server on your machine. It reads the real config file of 17 other AI tools (Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, OpenCode, Trae, Trae CN, Qoder, Gemini CLI, Qwen, Zed, Roo Code, Copilot CLI, Kiro, CodeBuddy, Continue) plus DeepSeek Harness itself, groups servers by the file that declares them, probes each one over JSON-RPC to see whether it starts and which tools it exposes, and gives every server a switch that mounts or unmounts it in DeepSeek Harness without editing the other tools' own files.

Read-only assessment of whether a Dameng DM8 database can be recovered and to which point (LSN or time), across 16 recovery scenarios, with an HTML report. Needs Java 8+ and a Dameng JDBC driver jar (DmJdbcDriver8.jar) that you provide yourself.

Adds job-role prompts to the DSH composer: type - at the start of the input to pick a role, which becomes a reference chip in the draft and is then injected as a system prompt section on every turn of that conversation, so the instruction keeps applying without showing up in the transcript. Roles are added and edited on a Settings page and stored in ~/.dsh/dsh-role-prompts.md.

Predicts your next message after each completed turn and shows it as ghost text in the composer: press → to accept, or keep typing and finish it word by word with Ctrl+→, Esc to dismiss. The prediction model follows the session by default or can be picked in the settings card, which also has an on/off switch and a speed test.

Keeps quotes out of the message body: quoting any passage from an assistant turn opens an editable quote tray above the composer, the quotes are injected into the next turn as system-prompt context (attributed with source and time), and an expandable quote row under that turn shows exactly which quotes were used. Quotes persist across page reloads and are claimed per turn; the host and client halves hand-shake on version and report a compatibility verdict.

Publishes whichever model the profile has selected in chat or on the Models page as an OpenAI-compatible HTTP endpoint: /v1/models, /v1/chat/completions (streaming SSE and non-streaming), /health. A request may name any routable model; one that omits `model` gets the current chat selection, so switching model in chat switches the endpoint. Switched on, it can also lend the model the Harness tools switched on individually, run those calls through the Harness tool runtime and feed results back up to a round limit. The listener is the plugin's own, so 127.0.0.1, 0.0.0.0 and a NAT-forwarded port all behave the same with no change to the request path. Settings cover bind address, port, API key with a generator, fallback provider and model, reasoning effort, CORS origin and timeout.